© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40736
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wali
    -0.08
    iments
    -0.08
    忱
    -0.08
    illions
    -0.07
    ẽ
    -0.07
    yka
    -0.07
    gaben
    -0.07
    ünft
    -0.07
    ingers
    -0.07
    æľ¬æ¥¼
    -0.07
    POSITIVE LOGITS
    igur
    0.07
    zech
    0.06
    èĤļçļ®
    0.06
    IS
    0.06
    æĥĬ天
    0.06
    ãĤ¦ãĥĪ
    0.06
     اÙĦÙĪØŃ
    0.06
    [U
    0.06
    [A
    0.06
    æĢİä¹Īæł·
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.